A novel local-phase method of automatic atlas construction in fetal ultrasound

Fathima, Sana; Rueda, Sylvia; Papageorghiou, Aris T.; Noble, J. Alison

doi:10.1117/12.878317

Cited by 5 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the context of aligning US data, the errors obtained from the proposed method are comparable with those reported by Fathima et al [29], who obtained a TRE of 3 ± 1 mm in US studies. However, these authors did the registration using 2D studies and without any artefacts.…”

Section: Resultssupporting

confidence: 86%

See 1 more Smart Citation

Probabilistic Learning Coherent Point Drift for 3D Ultrasound Fetal Head Registration

Perez‐Gonzalez

Cosı́o

Huegel

et al. 2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Quantification of brain growth is crucial for the assessment of fetal well being, for which ultrasound (US) images are the chosen clinical modality. However, they present artefacts, such as acoustic occlusion, especially after the 18th gestational week, when cranial calcification appears. Fetal US volume registration is useful in one or all of the following cases: to monitor the evolution of fetometry indicators, to segment different structures using a fetal brain atlas, and to align and combine multiple fetal brain acquisitions. This paper presents a new approach for automatic registration of real 3D US fetal brain volumes, volumes that contain a considerable degree of occlusion artefacts, noise, and missing data. To achieve this, a novel variant of the coherent point drift method is proposed. This work employs supervised learning to segment and conform a point cloud automatically and to estimate their subsequent weight factors. These factors are obtained by a random forest-based classification and are used to appropriately assign nonuniform membership probability values of a Gaussian mixture model. These characteristics allow for the automatic registration of 3D US fetal brain volumes with occlusions and multiplicative noise, without needing an initial point cloud. Compared to other intensity and geometry-based algorithms, the proposed method achieves an error reduction of 7.4% to 60.7%, with a target registration error of only 6.38 ± 3.24 mm. This makes the herein proposed approach highly suitable for 3D automatic registration of fetal head US volumes, an approach which can be useful to monitor fetal growth, segment several brain structures, or even compound multiple acquisitions taken from different projections.

show abstract

Section: Resultssupporting

confidence: 86%

“…is set of features was used to register studies in 2D and 3D using only one fetal brain. Fathima et al [29] reported a method based on representing each image by amplitude, orientation, and local phase. It is used to perform the affine registration based on normalized mutual information.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Learning Coherent Point Drift for 3D Ultrasound Fetal Head Registration

Perez‐Gonzalez

Cosı́o

Huegel

et al. 2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…This type of approaches can be useful for comparing different fetuses or to construct a head model representative of a population. A phase-based approach to guide registration of 2D US images was proposed by Fathima et al [131] . Firstly, a rigid registration using manually annotated skull ellipses is performed to place the images in the same reference space.…”

Section: Us Registration Methodsmentioning

confidence: 99%

A review of image processing methods for fetal head and brain analysis in ultrasound images

Torres

Morais

Oliveira

et al. 2022

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

“…Estos resultados son comparables con los reportados por Fathima et al [45], quienes obtuvieron un TRE de 3±1 mm en estudios de US en 2D. Ellos mencionan que un feto de segundo trimestre gestacional tiene una circunferencia craneal de entre 15-30 cm y un diámetro biparietal de 4.5 a 6 cm, por lo tanto un TRE en el rango de milímetros puede ser aceptable en la práctica clínica [45].…”

Section: Resultados Registrounclassified

“…Fathima et al [45] publicaron un trabajo, donde registraron un conjunto de 13 cerebros fetales de US en 2D con 20 semanas de gestación. Para esto, utilizaron un método donde representan cada imagen por su amplitud, orientación y fase local.…”

Section: Fetales Cerebrales De Usunclassified

Composición espacial de volúmenes cerebrales fetales de ultrasonido usando mapas probabilísticos

Pérez González

View full text Add to dashboard Cite

The project presented in this thesis constitutes one of the stages of a system, whose purpose is the semi-automatic evaluation of fetal health, through the measurement of several indices. This system is divided into four stages: composition and automatic segmentation of fetal structures; analysis of the movement of the fetal heart by means of optical flow techniques; extraction of maternal-fetal indicators from electrocardiographic recordings and automatic classification of the state of fetal health. The final aim is to assess the maternal-fetal health status, to help in the clinical screening of difficult cases and to implement this diagnostic tool in remote locations in a translational manner. In this work we present a contribution to one of the stages of the described system, which consists of the development of a new spatial composition method of brain ultrasound (US) volumes.

show abstract

A novel local-phase method of automatic atlas construction in fetal ultrasound

Cited by 5 publications

References 0 publications

Probabilistic Learning Coherent Point Drift for 3D Ultrasound Fetal Head Registration

Probabilistic Learning Coherent Point Drift for 3D Ultrasound Fetal Head Registration

A review of image processing methods for fetal head and brain analysis in ultrasound images

Composición espacial de volúmenes cerebrales fetales de ultrasonido usando mapas probabilísticos

Contact Info

Product

Resources

About